deepakkupanda

ValueError: Input and output must have the same number of spatial dimensions,

11

deepakpanda7/code/Users/deepakpanda/segmentation/mmsegmentation/work_dirs/pspnet_r101-d8_512x512_160k_p3m10k 2022-05-28 12:13:16,781 - mmseg - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) PolyLrUpdaterHook (NORMAL ) CheckpointHook (LOW ) DistEvalHook (VERY_LOW ) TextLoggerHook --------------------...

Training code and the MOS 600 benchmark

1

Hi Yang, Will it be possible for you to share the training code and the MOS 600 benchmark?

How to test frame interpolation on user videos?

1

I am trying to run frame interpolation on videos. I did not get the example in the document or the python file. please let me know if I have missed...

Images are saturated for adobe5k

2

Hi, I trained ZDCE++ in adobe5k for 100 epochs. I had kept 4000 images for training, 500 for validation and 500 for testing. I used the original folder for training....

Replace anything with ControlNet

4

I want to use ControlNet to replace anything such that foreground image shape does not change, only the background will change as per the text prompt. Can we do this?...

====Note: Using block-wise evaluation with block size=None, overlap=None, batch size=None ====This may generate unwanted block artefacts. Loading the model... Using model STMFNet to upsample file birthday_girl_720x480p.yuv 0%| | 0/641 [00:00